Deep learning improves contrast in low-fluence photoacoustic imaging

Hariri, Ali; Alipour, Kamran; Mantri, Yash; Schulze, Jürgen P.; Jokerst, Jesse V.

doi:10.1364/boe.395683

Cited by 69 publications

(64 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regardless of the source, the strong signal from skin can make detecting follicles under the skin surface challenging. Thus, we used a skin tracing technique (digital image processing) to remove signal from the skin surface to facilitate improved image formation [ 42 , 43 ]. Figure 4 D shows the skin trace from Figure 4 C. We removed the photoacoustic contribution from the skin surface to obtain Figure 4 E. Figure 4 F,G show the shaved stomach imaged at 690 and 850 nm, respectively.…”

Section: Resultsmentioning

confidence: 99%

Photoacoustic Imaging as a Tool for Assessing Hair Follicular Organization

Hariri

Moore

Mantri

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Follicular unit extraction (FUE) and follicular unit transplantation (FUT) account for 99% of hair transplant procedures. In both cases, it is important for clinicians to characterize follicle density for treatment planning and evaluation. The existing gold-standard is photographic examination. However, this approach is insensitive to subdermal hair and cannot identify follicle orientation. Here, we introduce a fast and non-invasive imaging technique to measure follicle density and angles across regions of varying density. We first showed that hair is a significant source of photoacoustic signal. We then selected regions of low, medium, and high follicle density and showed that photoacoustic imaging can measure the density of follicles even when they are not visible by eye. We performed handheld imaging by sweeping the transducer across the imaging area to generate 3D images via maximum intensity projection. Background signal from the dermis was removed using a skin tracing method. Measurement of follicle density using photoacoustic imaging was highly correlated with photographic determination (R2 = 0.96). Finally, we measured subdermal follicular angles—a key parameter influencing transection rates in FUE.

show abstract

Section: Resultsmentioning

confidence: 99%

Photoacoustic Imaging as a Tool for Assessing Hair Follicular Organization

Hariri

Moore

Mantri

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, their output energy is low, typically in the range of nJ/pulse to

. 118 The low energy leads to low signal intensity and thus reduced image quality. A favorable property of PLD/LED is that they have high repetition frequency, typically on the order of kHz and above.…”

Section: Applications Of DL In Paimentioning

confidence: 99%

“…used a modified U-Net, termed multi-level wavelet-CNN, in which the pooling operations were replaced by discrete wavelet transform (DWT), and pooling operations were replaced by DWT, and the upsampling operations were replaced by inverse wavelet transform, to enhance PA image quality in a low SNR setting. 118 They used the PA images taken at a fluence of

as the ground truth and then reduced the laser fluence down to 0.95 and

to train the network. In in vivo experiment, mice injected with various concentrations of methylene blue (MB) were imaged, and the CNR improvement factor was 1.55, 1.76, 1.62, and 1.48 for a dye concentration of 0.05, 0.1, 1.0, and 5.0 mM, respectively.…”

Section: Applications Of DL In Paimentioning

confidence: 99%

Deep learning in photoacoustic imaging: a review

et al. 2021

View full text Add to dashboard Cite

. Significance: Photoacoustic (PA) imaging can provide structural, functional, and molecular information for preclinical and clinical studies. For PA imaging (PAI), non-ideal signal detection deteriorates image quality, and quantitative PAI (QPAI) remains challenging due to the unknown light fluence spectra in deep tissue. In recent years, deep learning (DL) has shown outstanding performance when implemented in PAI, with applications in image reconstruction, quantification, and understanding. Aim: We provide (i) a comprehensive overview of the DL techniques that have been applied in PAI, (ii) references for designing DL models for various PAI tasks, and (iii) a summary of the future challenges and opportunities. Approach: Papers published before November 2020 in the area of applying DL in PAI were reviewed. We categorized them into three types: image understanding, reconstruction of the initial pressure distribution, and QPAI. Results: When applied in PAI, DL can effectively process images, improve reconstruction quality, fuse information, and assist quantitative analysis. Conclusion: DL has become a powerful tool in PAI. With the development of DL theory and technology, it will continue to boost the performance and facilitate the clinical translation of PAI.

show abstract

“…In an extensive study, the U-Net-based postprocessing approach was successfully applied to in vivo measurements 105 and showed clear improvements over backprojection-based algorithms when the data were undersampled or detected over a partial aperture (limited-view problem). Hariri et al 106 showed that this approach can improve in vivo imaging when using low-fluence sources. The observation of improved visual performance for in vivo applications was also reported in other studies.…”

Section: Application To In Vivo Imagingmentioning

confidence: 99%

Deep learning in photoacoustic tomography: current approaches and future directions

2020

View full text Add to dashboard Cite

Biomedical photoacoustic tomography, which can provide high-resolution 3D soft tissue images based on optical absorption, has advanced to the stage at which translation from the laboratory to clinical settings is becoming possible. The need for rapid image formation and the practical restrictions on data acquisition that arise from the constraints of a clinical workflow are presenting new image reconstruction challenges. There are many classical approaches to image reconstruction, but ameliorating the effects of incomplete or imperfect data through the incorporation of accurate priors is challenging and leads to slow algorithms. Recently, the application of deep learning (DL), or deep neural networks, to this problem has received a great deal of attention. We review the literature on learned image reconstruction, summarizing the current trends and explain how these approaches fit within, and to some extent have arisen from, a framework that encompasses classical reconstruction methods. In particular, it shows how these techniques can be understood from a Bayesian perspective, providing useful insights. We also provide a concise tutorial demonstration of three prototypical approaches to learned image reconstruction. The code and data sets for these demonstrations are available to researchers. It is anticipated that it is in in vivo applications-where data may be sparse, fast imaging critical, and priors difficult to construct by hand-that DL will have the most impact. With this in mind, we conclude with some indications of possible future research directions. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Deep learning improves contrast in low-fluence photoacoustic imaging

Cited by 69 publications

References 53 publications

Photoacoustic Imaging as a Tool for Assessing Hair Follicular Organization

Photoacoustic Imaging as a Tool for Assessing Hair Follicular Organization

Deep learning in photoacoustic imaging: a review

Deep learning in photoacoustic tomography: current approaches and future directions

Contact Info

Product

Resources

About